© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22511
    Prev
    Next
    INDEX
    Explanations

    design, create, relationship, Jews, first, HTML, trusted, hybrid, MAG

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -0.06
    æľ¬
    -0.05
     ~
    -0.05
     же
    -0.04
    1
    -0.04
    ,
    -0.04
    orne
    -0.04
     Ret
    -0.04
    otis
    -0.04
     under
    -0.04
    POSITIVE LOGITS
    Ouest
    0.07
     provinci
    0.07
    ersp
    0.07
     precau
    0.07
     bizar
    0.06
    Württemberg
    0.06
    æĶ¿
    0.06
     wesh
    0.06
    Ùģادة
    0.06
     concurr
    0.06
    Activations Density 0.050%

    No Known Activations